Training in progress, step 100

adapter_config.json

@@ -1,7 +1,7 @@
 {
   "alpha_pattern": {},
   "auto_mapping": null,
-  "base_model_name_or_path": "google/paligemma-3b-mix-448",
+  "base_model_name_or_path": "google/paligemma-3b-ft-ocrvqa-448",
   "bias": "none",
   "fan_in_fan_out": false,
   "inference_mode": true,
@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "o_proj",
+    "up_proj",
+    "q_proj",
     "down_proj",
     "k_proj",
-    "v_proj",
     "gate_proj",
-    "up_proj",
-    "o_proj",
-    "q_proj"
+    "v_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8908f41c5d6e39ccb9c88b12b781995d63bae36ea54dda6c04dd5f9b5a2205e5
+oid sha256:2dab3eb3238c19a2c97bd799bd8515e3d069d7ae2f9dc18dabc5e3a3268c1075
 size 45258384

runs/Dec02_12-45-40_DESKTOP-JQAT587/events.out.tfevents.1733168744.DESKTOP-JQAT587.41144.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d29dd36ebaddecf76e9f9fc4df70e0cdfcdf7e2d3bf739093538b7f0a95e06a
+size 5902

runs/Dec02_13-06-32_DESKTOP-JQAT587/events.out.tfevents.1733169993.DESKTOP-JQAT587.47776.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e55c38a675bb1b28d11eec9bb32fc1ffe9edc0108f6db3f8649d48bb46d8c0d9
+size 6375

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b7ed874ccb3ee1400e26ed417ea4a80a5d69e6bfc1c42eac0f20c92c5b39bcf9
+oid sha256:6ddbf842c0e2e6ba5a796ebf521400cac894b744ed0283d498ab50af0d3a2a85
 size 5240